© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 32109
    Prev
    Next
    INDEX
    Explanations

    her followed by specific endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erland
    -0.10
    éĴŁ
    -0.08
    heed
    -0.08
    heid
    -0.08
    urst
    -0.08
    nÃŃ
    -0.08
    erc
    -0.08
    ered
    -0.08
    vention
    -0.08
     garg
    -0.08
    POSITIVE LOGITS
     Majesty
    0.14
    locker
    0.13
    editary
    0.13
    amient
    0.11
    unter
    0.11
    icy
    0.11
    cept
    0.11
     maj
    0.11
    /her
    0.11
    sey
    0.11
    Activations Density 0.045%

    No Known Activations